Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    CHOOL
    -0.07
     funcs
    -0.06
    光荣
    -0.06
    legant
    -0.06
    呼吸
    -0.06
    real
    -0.06
    mega
    -0.06
    Migration
    -0.06
     Urban
    -0.06
    民办
    -0.06
    POSITIVE LOGITS
    .KeyEvent
    0.08
    عائلة
    0.07
     rewind
    0.07
     Familie
    0.07
    尤其是
    0.07
    㸆
    0.07
     Indones
    0.07
     sagte
    0.07
     חברים
    0.07
    ,size
    0.07
    Act Density 0.071%

    No Known Activations